© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 15201
    Prev
    Next
    INDEX
    Explanations

    references to legal or criminal activities and investigations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    946
    +0.13
    0.4%
    1013
    +0.10
    0.3%
    1499
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.13
    0.06
    939
    +0.10
    0.04
    1499
    +0.09
    0.04
    Negative Logits
     cushi
    -0.67
     horrend
    -0.50
     vuol
    -0.49
     prouve
    -0.49
     échou
    -0.49
     apparti
    -0.47
     notare
    -0.47
     ferait
    -0.47
     ruine
    -0.47
     migli
    -0.47
    POSITIVE LOGITS
    romptu
    0.56
     raided
    0.54
     raid
    0.54
    atience
    0.53
    lacable
    0.49
    etermined
    0.49
     läm
    0.47
    Personensuche
    0.47
    YNAMIC
    0.46
     raids
    0.46
    Activations Density 0.339%

    No Known Activations